English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generative Adversarial Networks (GANs) have gained significant attention inseveral computer vision tasks for generating high-quality synthetic data.Various medical applications including diagnostic imaging and radiation therapycan benefit greatly from synthetic data generation due to data scarcity in thedomain. However, medical image data is typically kept in 3D space, andgenerative models suffer from the curse of dimensionality issues in generatingsuch synthetic data. In this paper, we investigate the potential of GANs forgenerating connected 3D volumes. We propose an improved version of 3D$\alpha$-GAN by incorporating various architectural enhancements. On asynthetic dataset of connected 3D spheres and ellipsoids, our model cangenerate fully connected 3D shapes with similar geometrical characteristics tothat of training data. We also show that our 3D GAN model can successfullygenerate high-quality 3D tumor volumes and associated treatment specifications(e.g., isocenter locations). Similar moment invariants to the training data aswell as fully connected 3D shapes confirm that improved 3D $\alpha$-GANimplicitly learns the training data distribution, and generatesrealistic-looking samples. The capability of improved 3D $\alpha$-GAN makes ita valuable source for generating synthetic medical image data that can helpfuture research in this domain.

Improved $\alpha$-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planning